Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is covered. The description adds no behavioral context beyond the field list: no indication of snapshot freshness, aggregation window, units, or whether the figures are live vs. cached — notable gaps for an openWorldHint data tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single short fragment with no padding, so nothing is wasted. But it is under-specified rather than concise: a sentence frame ('Returns protocol-wide ...') would have cost two more words and removed the ambiguity about scope.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no parameters, the description is the only source of information about the return value, and it names four metric families without units, structure, or scope. For a parameterless stats endpoint, an agent still cannot tell what shape the response takes or whether 'per-market use of caps' is keyed by market id.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the schema baseline of 4 applies. The description's field enumeration is consistent with a parameterless aggregate call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates what the tool returns (TVL, treasury fees, liquidations, per-market cap usage), which tells an agent the resource is protocol-level statistics. However, it is a noun fragment with no verb and no scope statement (protocol-wide vs. filtered by market/account), and it does nothing to distinguish it from siblings like get_health, get_market, or get_series_settlement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this versus get_health, get_market, or get_events. The agent must infer from the metric list alone that this is the aggregate-dashboard call, and there is no statement of prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.